statistical-power
1 finding (1 high), mainly resource abuse. Most recent scan 2026-10-21.
Second scanner: NVIDIA SkillSpector
Independent static run, no language model, over the same files as the Cisco scan above. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Calculates sample sizes and statistical power for study planning. Applies when someone asks "how many subjects/samples/replicates do I need", wants an a priori power analysis, a minimum detectable effect (MDE), a power curve, or needs to justify a sample size for a grant, IRB protocol, or pre-registration. Covers closed-form power for t-tests, ANOVA, proportions, correlations, chi-square, and regression, plus simulation-based (Monte Carlo) power for complex designs — logistic/Poisson regression, mixed models, cluster-randomized trials, survival, and interactions. Also handles requests that…
- Package
- 6 files, 77 KB
- SKILL.md
- 2272 words, 12+ sections
- Code
- Python (2)
- Allowed tools
ReadWriteEditBash- License
- MIT license
- Compatibility
- Requires Python >=3.12 with statsmodels, scipy, numpy, pandas, and matplotlib. Optional comparison uses pingouin; survival extensions use lifelines (requires pandas<3). Installation needs network access unless packages are cached. Calculations run locally without credentials.
SKILL.md covers: Statistical Power & Sample Size · Overview · When to Use This Skill · Installation · Optional comparison / survival methods (also checked for current API use): · The one decision that drives everything: the effect size · Quick recipes (closed-form) · 1. How many per group to detect Cohen's d = 0.5, two-sided, 80% power? · -> 64 in sample 1; equal allocation gives 64 in sample 2 · 2. Two groups, 3:1 allocation (e.g. more controls than cases) · 3. Fixed n=30/group — what's the minimum detectable d at 80% power? · 4. One-way ANOVA, 4 groups, detect Cohen's f = 0.25
Findings
HIGH Infinite loop without clear exit condition Resource Abusestatic
Pattern detected: while True:
scripts/simulate_power.py:158
while True:What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 17 KB |
references/closed_form_recipes.md | doc | 11 KB |
references/effect_sizes.md | doc | 6.0 KB |
references/simulation_based_power.md | doc | 9.9 KB |
scripts/power.py | script | 19 KB |
scripts/simulate_power.py | script | 13 KB |
External hosts referenced
doi.org www.statsmodels.org docs.scipy.org github.com arxiv.org lifelines.readthedocs.io export.arxiv.org numpy.org
Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.
Package contents recorded 2026-10-22 at commit 593377bb0487. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Bytecode analyzer.
- Pipeline analyzer.
- Correlation analyzer.
- Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
- Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://github.com/K-Dense-AI/scientific-agent-skills
- Raw scan result: skills-statistical-power-scan.json
- Badge for your README:
- Request a re-scan